Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14726
    Prev
    Next
    INDEX
    Explanations

    terms related to prohibition or restriction

    oai_token-act-pair · gpt-3.5-turbo

    words related to prohibitions or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sie
    -0.81
    framework
    -0.80
    wm
    -0.71
    wake
    -0.71
    lycer
    -0.70
    reset
    -0.69
    holm
    -0.69
    dds
    -0.69
    factor
    -0.68
    ead
    -0.68
    POSITIVE LOGITS
     imports
    0.99
     smoking
    0.88
     discrimination
    0.87
     outright
    0.86
     abortions
    0.85
     anyone
    0.84
     unauthorized
    0.83
     importing
    0.82
     exporting
    0.80
     outsiders
    0.80
    Activations Density 0.084%

    No Known Activations